© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3053
    Prev
    Next
    INDEX
    Explanations

    periods or experiences

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects explicit mentions of having a positive or enjoyable experience, especially when framed with words like “evening,” “experience,” or “time.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uu
    0.68
    uuuu
    0.68
    uries
    0.62
    Firefox
    0.62
    uki
    0.60
    <0x9B>
    0.59
    uo
    0.59
    errno
    0.59
    دارة
    0.59
     sporadic
    0.59
    POSITIVE LOGITS
     Продол
    0.73
     עם
    0.70
     withd
    0.69
     with
    0.68
     همراه
    0.68
     معه
    0.65
    ជាមួយនឹង
    0.65
     ร่วม
    0.64
    姏
    0.63
    with
    0.62
    Activations Density 0.029%

    No Known Activations